langchain-ai/docs

langgraph-docs

Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API,…

Idioma do texto original: inglês

docs-code-samples

Use this skill when migrating inline code samples from LangChain docs (MDX files) into external, testable code files that are extracted by this repo’s snippet scripts and used as Mintlify snippets. Applies when extracting code blocks from documentation,…

Idioma do texto original: inglês

update-integrations-prs

Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override). Rebase an integration PR, convert to external YAML, feature an integration, or check package downloads for docs…

Idioma do texto original: inglês

langchain

Build agents with a prebuilt architecture and integrations for any model or tool. Use when creating tool-calling agents, switching model providers, or adding structured output.

Idioma do texto original: inglês

deep-agents

Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution. Use for complex, multi-step tasks that need built-in capabilities.

Idioma do texto original: inglês

langgraph

Build stateful, durable agent workflows with LangGraph. Use when you need custom graph-based control flow, human-in-the-loop, persistence, or multi-agent orchestration.

Idioma do texto original: inglês

pandas-patterns

Common pandas and matplotlib patterns for data analysis and visualization

Idioma do texto original: inglês

langsmith

Trace, evaluate, and deploy AI agents and LLM applications with LangSmith. Use when adding observability, running evaluations, engineering prompts, or deploying agents to production.

Idioma do texto original: inglês

write-timestamp

Use when the user wants the current date and time written to a file via the bundled script inside the sandbox.

Idioma do texto original: inglês